© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118647
    Prev
    Next
    INDEX
    Explanations

    phrases related to benefits and efficiencies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ек
    -0.07
    ilogy
    -0.07
    ifar
    -0.06
     Pty
    -0.06
    icz
    -0.06
    razier
    -0.06
    acie
    -0.06
     Bu
    -0.06
     maint
    -0.06
    lando
    -0.06
    POSITIVE LOGITS
     benefits
    0.22
     Benefits
    0.18
     benefit
    0.18
    Benefits
    0.17
    benef
    0.15
     Benefit
    0.14
    Benef
    0.13
     advantages
    0.13
     benefiting
    0.13
     béné
    0.13
    Activations Density 0.082%

    No Known Activations